Merge Models
Collection
Models I merged using mergekit library
•
5 items
•
Updated
•
4
merged
This is a merge of pre-trained language models created using mergekit.
You can use ChatML format.
Merge Method
This model was merged using the SLERP merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
base_model: rombodawg/Rombos-LLM-V2.5-Qwen-7b
dtype: bfloat16
merge_method: slerp
parameters:
t:
- filter: self_attn
value: [0.0, 0.5, 0.3, 0.7, 1.0]
- filter: mlp
value: [1.0, 0.5, 0.7, 0.3, 0.0]
- value: 0.5
slices:
- sources:
- layer_range: [0, 28]
model: rombodawg/Rombos-LLM-V2.5-Qwen-7b
- layer_range: [0, 28]
model: Cran-May/T.E-8.1
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 27.34 |
| IFEval (0-Shot) | 69.25 |
| BBH (3-Shot) | 36.50 |
| MATH Lvl 5 (4-Shot) | 0.83 |
| GPQA (0-shot) | 8.17 |
| MuSR (0-shot) | 10.98 |
| MMLU-PRO (5-shot) | 38.28 |
- Downloads last month
- 9
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for suayptalha/Rombos-2.5-T.E-8.1
Collection including suayptalha/Rombos-2.5-T.E-8.1
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard69.250
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard36.500
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard0.830
- acc_norm on GPQA (0-shot)Open LLM Leaderboard8.170
- acc_norm on MuSR (0-shot)Open LLM Leaderboard10.980
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard38.280